Agenzia Giornalistica
direttore Paolo Pagliaro

Goodbye plagiarism, a made in Italy method to create new melodies

BigItaly focus
BigiItalyfocus is a daily news service offering informations and insights on the best of the italian presence in the world.
From Monday to Friday, BigItalyFocus provides an information overview, ranged from development aid to made in Italy

Goodbye plagiarism, a made in Italy method to create new melodies

(September 4, 2017) A statistical method to capture musical styles and create new melodies. A pattern that can also be used to avoid plagiarism. It has a touch of made in Italy the innovative research published on Scientific Reports. From the statistical principles, a new method for finding the main structures of musical melodies is born. It is the discovery of an international research team, which includes Vittorio Loreto and Francesca Tria of the University of Rome La Sapienza, which has demonstrated as a new method is able to identify the fundamental association structures in a musical sequence. The model can also be used to artificially create musical pieces of the same style, while avoiding plagiarism. Music is a system composed of a complex network of interacting components, notes, comparable to neurons in the nervous system; the statistic, through the probability calculation method, is able to detect the existing relationships between the notes and to guide the algorithmic composition of new melodies. The challenge of the research group was to find a model of Maximum Entropy for determining probability distributions from "partial" information, capable of generating new melodies with the same stylistic elements as the reference track . Given a sequence of elements, in this case the notes, one can determine for each pair of "x" and "y" notes, the probability that "x" is followed by "y"; From this set of probabilities, a random sequence can be obtained by digital processing, which holds the same probabilities: from a given corpus of tracks, the method is able to generate, using a specific algorithm, musical tracks with the same style as reference corpus (PO / red)


ABOUT / THE EXPERT

"To avoid plagiarism," explains Vittorio Loreto, Professor of Physics at La Sapienza, "we use a special algorithm to limit the length of copy sequences in artificially generated songs. By using compression algorithms we can then verify both the proximity of the new composition to the reference corpus and the degree of plagiarism. In this way you can control the balance between innovation and similarity. " "Its generality", adds Loreto, "gives our model greater freedom in creating new melodies that echo the style of a given piece of music and opens up a series of applications both in the music field (to address issues related to rhythm, polyphony and expressiveness) and in other areas (such as language or art) where stylistic and creative elements are crucial elements, including in the great debate on artificial creativity and creative interactions between humans and machines. "

(© 9Colonne - citare la fonte)